search

LARG / HFO

Half Field Offense in Robocup 2D Soccer
MIT License
228 stars 93 forks source link

Wrapper for Reinforcement Learning research #109

Open lafmdp opened 4 years ago

lafmdp commented 4 years ago

We package HFO environment as a gym-style env and the implementation is as follow: https://github.com/lafmdp/hfo_rl_env/blob/master/utils/env_wrapper.py

Reward function is drew lessons from https://github.com/LARG/HFO/blob/master/example/sarsa_offense/high_level_sarsa_agent.py

mhauskn commented 4 years ago

Thanks for the pointer!